Nobleblocks MCP Server

Search 340M+ academic papers — citation graphs, semantic similarity, and AI literature reviews.

Remote serverstreamable-httpPython

What is the Nobleblocks MCP server?

Most developer tooling work still happens through a UI a human drives. Nobleblocks MCP server moves it into the conversation instead. Search 340M+ academic papers — citation graphs, semantic similarity, and AI literature reviews.

The short version

Search 340 million deduplicated academic papers from Claude Desktop, Claude Web, ChatGPT, Cursor, VS Code Copilot, or any MCP-compatible tool. Covers 15+ academic databases — all cross-linked through a biomedical knowledge graph with 1.3M+ entities and 109M+ paper connections.

The tools it exposes

The server publishes 6 tools. What each one is for:

  • search_papers — Full-text + semantic hybrid search with year/citation/source filters
  • get_paper — Fetch metadata by DOI, PMID, arXiv ID, or OpenAlex ID
  • find_similar — Find papers related by meaning, not just keyword matching
  • get_citation_graph — Citation network — references and citing papers
  • search_by_entity — Find papers linked to a gene, drug, disease, or institution via the KG
  • create_literature_review — AI-generated structured lit review with citations (Pro)

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

What it needs from you

Configuration is passed through the environment: NOBLEBLOCKS_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

How it compares

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Nobleblocks's toolset — search_papers, get_paper, find_similar and 3 more — is a fair guide to whether it matches your workflow. It is maintained by com.nobleblocks; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
search_papersFull-text + semantic hybrid search with year/citation/source filters
get_paperFetch metadata by DOI, PMID, arXiv ID, or OpenAlex ID
find_similarFind papers related by meaning, not just keyword matching
get_citation_graphCitation network — references and citing papers
search_by_entityFind papers linked to a gene, drug, disease, or institution via the KG
create_literature_reviewAI-generated structured lit review with citations (Pro)

How to install the Nobleblocks MCP server

{
  "mcpServers": {
    "nobleblocks": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/inspector"],
      "env": {
        "NOBLEBLOCKS_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
NOBLEBLOCKS_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Nobleblocks to search papers.
  • Use Nobleblocks to get paper.
  • Use Nobleblocks to find similar.

Frequently asked questions

It connects Nobleblocks to MCP-compatible AI assistants such as Claude and Cursor, exposing 6 tools (search_papers, get_paper, find_similar, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Nobleblocks directly.